公开(公告)号：US20190021068A1

公开(公告)日：2019-01-17

申请号：US16136827

申请日：2018-09-20

Applicant: Huawei Technologies Co., Ltd.

Inventor： Mingxuan Yuan ,  Jia Zeng ,  Xialiang Tong

IPC: H04W64/00 ,  H04W4/021 ,  G01S5/02 ,  G06N5/04 ,  G06F15/18

CPC classification number: H04W64/003 ,  G01S5/0252 ,  G06N5/042 ,  G06N20/00 ,  H04W4/021 ,  H04W64/00

Abstract: A terminal positioning method and a network device, where the network device obtains radio signal sampling information of a first terminal at a current moment. The first terminal is any terminal in a target region, and the target region is a preset geographic region. The network device obtains position information of the first terminal at the current moment by prediction based on the radio signal sampling information of the first terminal at the current moment and a predictive model of the target region. The predictive model is obtained by extensive data training in the target region, has relatively strong error tolerance and error-correction capabilities, and can accurately reflect a relationship between radio signal sampling information and position information of a terminal. Terminal positioning accuracy is effectively improved.

公开(公告)号：US10542519B2

公开(公告)日：2020-01-21

申请号：US16136827

申请日：2018-09-20

Applicant: Huawei Technologies Co., Ltd.

Inventor： Mingxuan Yuan ,  Jia Zeng ,  Xialiang Tong

IPC: H04W4/00 ,  H04W64/00 ,  G06N20/00 ,  G01S5/02 ,  G06N5/04 ,  H04W4/021

Abstract: A terminal positioning method and a network device, where the network device obtains radio signal sampling information of a first terminal at a current moment. The first terminal is any terminal in a target region, and the target region is a preset geographic region. The network device obtains position information of the first terminal at the current moment by prediction based on the radio signal sampling information of the first terminal at the current moment and a predictive model of the target region. The predictive model is obtained by extensive data training in the target region, has relatively strong error tolerance and error-correction capabilities, and can accurately reflect a relationship between radio signal sampling information and position information of a terminal. Terminal positioning accuracy is effectively improved.